CN104794064A - Cache management method based on region heat degree - Google Patents
Cache management method based on region heat degree Download PDFInfo
- Publication number
- CN104794064A CN104794064A CN201510187454.9A CN201510187454A CN104794064A CN 104794064 A CN104794064 A CN 104794064A CN 201510187454 A CN201510187454 A CN 201510187454A CN 104794064 A CN104794064 A CN 104794064A
- Authority
- CN
- China
- Prior art keywords
- data block
- region
- buffer memory
- hot value
- hash table
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Abstract
The invention discloses a cache management method based on the region heat degree. By screening data blocks, only the hotspot data blocks are cached, replacement operation conducted after a cache is fully written is reduced, and therefore the cache hit rate is increased, and the service life of SSD is prolonged. The method specifically includes the steps of firstly, establishing a harsh table and a binary tree, conducting initialization, and recording disk region numbers, heat degree values corresponding to all disk regions, points of two subregions pointing leftwards and rightwards, and the heat degree values of the subregions; secondly, renewing information of the hash table and the binary tree for the reading and writing request of each time according to the sizes of disk regions and addresses corresponding to the reading and writing request data blocks; thirdly, screening out the data blocks to which a user frequently has access according to the region heat degree values, and writing data in the data blocks into the cache. By means of the cache management method of conducting screening and then conducting writing, the cache hit rate can be increased, the replacement operation of cache data is reduced, and the service life of solid state disk caches is prolonged.
Description
Technical field
The invention belongs to computer information storage technology field, more specifically, relate to a kind of buffer memory management method based on region temperature.
Background technology
The mechanically actuated such as tracking and location of disk when reading and writing data creates rotational latency, makes disk response speed be much more slowly than internal memory, causes the performance bottleneck of whole storage system thus.In order to improve system storage speed, between disk and internal memory, add one deck can access data buffer memory device at high speed; In disk storage system, the effect of buffer memory is exactly the access speed of the hot spot data acceleration disk by being accessed frequently in memory disk, so these hot spot datas just can directly read from buffer memory, shorten the data response time, improve the performance of whole disk storage system, but the buffer memory device price general charged can carrying out high speed data access is higher and buffer memory capacity is limited.Cache management is exactly will make full use of limited buffer memory capacity to store hot spot data as much as possible, improves buffer memory device utilization factor, to improve the performance of whole disk storage system.Compared with traditional magnetic disk, solid state hard disc (SSD) is a kind of electronic equipment, the delay that mechanical rotation process causes, and has random I/O performance high, energy consumption is low, and noise is little, the advantage that shock resistance is good, but capacity is little, cost is high, and erasing times is limited, has the restriction in serviceable life; The pattern that mixing stores is adopted, using the L2 cache of solid state hard disc as disk in a lot of storage products.
In order to improve cache hit rate, extend SSD serviceable life, traditional cache replacement algorithm mainly considers temporal locality and the dsc data of access, and the statistical method of dsc data is mainly based on the visit capacity of each block in unit period, these methods are not suitable for directly applying to the disk buffering based on SSD; First, SSD relative to level cache (internal memory), has more weak temporal locality as L2 cache; Secondly, large quantity research shows that buffer memory dsc data and replacement (FBR) algorithm based on access frequency are better than this algorithm based on temporal locality of picture LRU; But, the statistics of dsc data is generally the access frequency based on disk block, this just needs a temperature computation process, the frequent replacement between dsc data or between cold and hot data may be caused in temperature computation process, not only performance can be affected, also cause a large amount of the writing of SSD, shorten the serviceable life of SSD.
Summary of the invention
For above defect or the Improvement requirement of prior art, the invention provides a kind of buffer memory management method based on region temperature, its object is to by the screening to data block, buffer memory hot spot data block, decrease buffer memory and write the replacement operation completely, improve cache hit rate thus, extend SSD serviceable life.
For achieving the above object, according to one aspect of the present invention, provide a kind of buffer memory management method based on region temperature, specific as follows:
(1) in internal memory, Hash table and binary tree is created, and initialization Hash table and binary tree; The hot value adopting Hash table recording disc regional number, each disk areas corresponding and two point to the pointer of left and right subregions; Binary tree is adopted to preserve the hot value of subregion; Wherein, subregion refers to that each region is divided the region of rear correspondence again;
(2) for each read-write requests, the hot value in each region in Hash table is upgraded according to disk areas size and address corresponding to read-write requests data block; Reduce by half according to the hot value of hot value damped cycle by each region simultaneously, and upgrade subregion hot value in binary tree;
(3) data block of frequent access is filtered out according to region hot value, by the data write buffer memory in this data block; Because the most of hot spot data on disk is mainly distributed in several specific region; Therefore first filter out these data blocks be accessed frequently, then write in the buffer memory of finite capacity, the hit rate of buffer memory can be improved, reduce data cached replacement operation simultaneously, extend the serviceable life of solid state hard disc buffer memory.
Preferably, in step (1), the value that the initialization value of Hash table size obtains divided by each area size for disk block quantity, all initialization values of hash table and binary tree are all 0.
Preferably, in step (2), the process of update area hot value is specific as follows:
(2.1) when a read-write requests arrives, Region dividing is carried out to disk, obtains regional number;
(2.2) hash table that seek area is corresponding in Hash table, and the hot value in this region is increased by 1;
(2.3) if current total access times are integral multiples of hot value damped cycle, then the region hot value of correspondence is reduced by half, the subregion hot value of correspondence is reduced by half simultaneously;
(2.4) when region hot value is kept to 0, then corresponding hash table is emptied, to record new area information; Wherein, regional number is obtained divided by area size by LBA (Logical Block Addressing).
Preferably, filter out the process of the data block of frequent access according to region hot value specific as follows for step (3):
(3.1) judge whether request msg hits buffer memory; If so, step (3.10) is then entered; If not, then step (3.2) is entered;
(3.2) judge whether buffer memory has been write full; If so, step (3.4) is entered; If not, then step (3.3) is entered;
(3.3) request msg is write free buffer block, form requested data block, and requested data block is inserted cache blocks queue tail, then enter step (3.10);
(3.4) from the head of buffer queue, according to the principle of first in first out, obtain a cache blocks, then enter step (3.5);
(3.5) judge whether the cache blocks obtained in requested data block and step (3.4) belongs to the same area; If so, step (3.6) is then entered; If not, then step (3.7) is entered;
(3.6) judge whether requested data block and caching data block belong to same subregion, if so, then enter step (3.4), from buffer queue, obtain next cache blocks; If not, then step (3.7) is entered;
(3.7) from Hash table, region temperature PrA corresponding to the cache blocks region temperature PrB corresponding with requested data block is searched respectively by data block number; If PrB is greater than c*PrA, then enter step (3.10); Otherwise, enter step (3.8); Wherein c is comparative factor;
(3.8) repeat step (3.4) ~ (3.7), until requested data block region temperature is completeer with the region temperature of data blocks all in buffer queue, enter step (3.9);
(3.9) read-write requests is directed to address corresponding to disk, requested data block is write disk;
(3.10) read-write requests is directed to address corresponding to current cache, requested data block is write the space at the cache blocks place of current selection;
Wherein, buffer queue is a fifo queue, for recording the data be buffered; Hash table have recorded temperature and the regional number in each region; Region temperature counts with access times and reduces by half according to the damped cycle preset, and damped cycle calculates according to request access number of times; Regional number is divided by with the area size preset by the disk block number of request to obtain.
The advantage of above step (3) is: control the request msg of miss buffer memory, to screen the request msg of write buffer memory, reduces buffer memory replacement operation.
Preferably, comparative factor c gets the value being greater than 1; Comparative factor is greater than 1 and shows: only have the hot value when requested data block to exceed the hot value being buffered block and reach the replacement of a certain amount of just execution buffer memory, but not equivalence ratio comparatively; Can replace by delay buffer like this, effectively stop frequent replacement.
Preferably, due to the cold data of non-frequent access may be there are in disk areas, each disk areas Further Division is become the subregion that two equal, and manage subregion by binary tree, improve the accuracy identifying dsc data thus.
The buffer memory management method that the present invention proposes is preferably buffer memory medium with solid state hard disc, but its application is not limited to disk storage system.
In general, the above technical scheme conceived by the present invention compared with prior art, can obtain following beneficial effect:
(1) buffer memory management method based on region temperature of the present invention's proposition, utilize the hot value in simple Hash table and each region of binary tree structure record, by comparing region hot value corresponding to each disk block, filter out the region unit that in whole disk, access frequency is the highest to preserve in the buffer, improve cache hit rate; Decrease buffer memory simultaneously and write the replacement operation completely, thus the write operation decreased solid state hard disc, compared with writing the buffer memory management method of buffer memory with the existing data block by non-frequent access, in the serviceable life extending solid state hard disc, there is good effect;
(2) buffer memory management method based on region temperature of the present invention's proposition, compare and calculate hot spot data in units of disk block, in units of region, calculate temperature can accelerate temperature accumulative process, further reduce the unnecessary replacement operation that accumulative process causes, utilize region temperature to decide buffer memory thus whether to replace, not only can improve the accuracy of hot spot data identification, the accumulative process of temperature can also be accelerated.
Accompanying drawing explanation
Fig. 1 is the schematic diagram of the system of the method application of the embodiment of the present invention 1;
Fig. 2 is the implementing procedure figure of the buffer memory management method that the embodiment of the present invention 1 provides;
Fig. 3 is the caching data block screening process figure of the embodiment of the present invention 1;
Fig. 4 is the cache hit rate of the embodiment of the present invention 1 and the comparison diagram of other method;
Fig. 5 is that the buffer memory of the embodiment of the present invention 1 replaces the comparison diagram with other method.
Embodiment
In order to make object of the present invention, technical scheme and advantage clearly understand, below in conjunction with drawings and Examples, the present invention is further elaborated.Should be appreciated that specific embodiment described herein only in order to explain the present invention, be not intended to limit the present invention.In addition, if below in described each embodiment of the present invention involved technical characteristic do not form conflict each other and just can mutually combine.
Buffer memory management method based on region temperature provided by the invention is preferably applied in the storage system using solid state hard disc as buffer memory medium as shown in Figure 1, but its application is not limited to this type of disk storage system.
As shown in Figure 2, being the process flow diagram of the buffer memory management method based on region temperature provided by the invention, by controlling the request msg of miss buffer memory, to screen the request msg of write buffer memory, reaching the object reducing buffer memory replacement operation.
Specifically buffer memory management method provided by the invention is set forth below in conjunction with embodiment 1; In embodiment 1, adopt cache simulator Cachesim, example is applied as with Webproxy (a kind of webpage mailbox agency and online course load management), by carrying out buffer control to read-write requests data, filter out the highest region unit of access frequency and preserved in the buffer, improve cache hit rate, avoid unnecessary buffer memory replacement operation simultaneously; Specific as follows:
(1) Hash table and binary tree structure is created and initialization; The hot value adopting Hash table recording disc regional number, each disk areas corresponding and two point to the pointer of left and right subregions; Binary tree is adopted to preserve the hot value of subregion; Area size is set to 4 disk block sizes, and damped cycle is 1,600,000 requests, and Hash table size is initialized as disk block quantity divided by area size, and Depth of Binary Tree is 2, and all values of hash table and binary tree structure is all initialized as 0, and comparative factor c is 1.4;
(2) upgrade Hash table and binary tree information according to area size and damped cycle: for each read-write requests, upgrade the hot value in each region in Hash table according to disk areas size and address corresponding to read-write requests data block; Reduce by half according to the hot value of hot value damped cycle by each region simultaneously, and upgrade subregion hot value in binary tree; If hot value is kept to 0, empty corresponding hash table, to record new area information;
(3) the data area write buffer memory of the frequent access of screening: the data block filtering out frequent access according to region hot value, by the data write buffer memory in this data block;
In practical application load, the hot spot data block of frequent access only accounts for a small part, and the most of hot spot data on disk is mainly distributed in several specific region; Therefore first filter out these data areas be accessed frequently, then the hit rate of buffer memory can be improved in the buffer memory writing finite capacity, reduce data cached replacement operation simultaneously, extend the serviceable life of solid state hard disc buffer memory;
(4) cache management and read-write requests are redirected.
Wherein, the screening process in step (3) is as shown in Figure 3, specific as follows:
(3.1) judge whether request msg hits buffer memory; If so, step (3.10) is then entered; If not, then step (3.2) is entered;
(3.2) judge whether buffer memory has been write full; If so, step (3.4) is entered; If not, then step (3.3) is entered;
(3.3) request msg is write free buffer block, form requested data block, and requested data block is inserted cache blocks queue tail, then enter step (3.10);
(3.4) from the head of buffer queue, according to the principle of first in first out, obtain a cache blocks, then enter step (3.5);
(3.5) judge whether the cache blocks obtained in requested data block and step (3.4) belongs to the same area; If so, step (3.6) is then entered; If not, then step (3.7) is entered;
(3.6) judge whether requested data block and caching data block belong to same subregion, if so, then enter step (3.4), from fifo queue, obtain next cache blocks; If not, then step (3.7) is entered;
(3.7) from Hash table, region temperature PrA corresponding to the cache blocks region temperature PrB corresponding with requested data block is searched respectively by data block number; If PrB is greater than c*PrA, then enter step (3.10); Otherwise, enter step (3.8);
(3.8) repeat step (3.4) ~ (3.7), until requested data block region temperature is completeer with the region temperature of data blocks all in buffer queue, enter step (3.9);
(3.9) read-write requests is directed to address corresponding to disk, requested data block is write disk;
(3.10) read-write requests is directed to address corresponding to current cache, requested data block is write the space at the cache blocks place of current selection.
Be the test result of embodiment 1 hit rate shown in Fig. 4, wherein, RAC represents caching method provided by the invention; 1 buffer memory embodiment illustrated in fig. 5 replaces the test result of number of times; Analyze from test result and learn, buffer memory management method provided by the invention is obviously superior than other method in hit rate and buffer memory replace two: with LARC, ARC, MQ, these methods of FIFO with LRU are compared, and not only increase hit rate and decrease buffer memory replacement operation simultaneously; Replace owing to decreasing unnecessary in a large number buffer memory, because this reducing number of times being write to SSD, extending the serviceable life of SSD thus.
Those skilled in the art will readily understand; the foregoing is only preferred embodiment of the present invention; not in order to limit the present invention, all any amendments done within the spirit and principles in the present invention, equivalent replacement and improvement etc., all should be included within protection scope of the present invention.
Claims (6)
1., based on a buffer memory management method for region temperature, it is characterized in that, specific as follows:
(1) in internal memory, Hash table and binary tree is created, and initialization Hash table and binary tree; The hot value adopting Hash table recording disc regional number, each disk areas corresponding and two point to the pointer of left and right subregions; Binary tree is adopted to preserve the hot value of subregion;
(2) for each read-write requests, the hot value in each region in Hash table is upgraded according to disk areas size and address corresponding to read-write requests data block; Reduce by half according to the hot value of hot value damped cycle by each region simultaneously, and upgrade subregion hot value in binary tree;
(3) data block of frequent access is filtered out according to region hot value, by the data write buffer memory in this data block.
2. buffer memory management method as claimed in claim 1, it is characterized in that, in described step (1), the value that the initialization value of Hash table size obtains divided by each area size for disk block quantity, all initialization values of hash table and binary tree are 0.
3. buffer memory management method as claimed in claim 1 or 2, it is characterized in that, in described step (2), the process of update area hot value is specific as follows:
(2.1) when a read-write requests arrives, Region dividing is carried out to disk, obtains regional number;
(2.2) hash table that seek area is corresponding in Hash table, and the hot value in this region is increased by 1;
(2.3) if current total access times are integral multiples of hot value damped cycle, then the region hot value of correspondence is reduced by half, the subregion hot value of correspondence is reduced by half simultaneously;
(2.4) when region hot value is kept to 0, then corresponding hash table is emptied, to record new area information; Wherein, regional number is obtained divided by area size by LBA (Logical Block Addressing).
4. the buffer memory management method as described in any one of claims 1 to 3, is characterized in that, described step (3) filters out the data block of frequent access process according to region hot value is specific as follows:
(3.1) judge whether request msg hits buffer memory; If so, step (3.10) is then entered; If not, then step (3.2) is entered;
(3.2) judge whether buffer memory has been write full; If so, step (3.4) is entered; If not, then step (3.3) is entered;
(3.3) request msg is write free buffer block, form requested data block, and requested data block is inserted cache blocks queue tail, then enter step (3.10);
(3.4) from the head of buffer queue, according to the principle of first in first out, obtain a cache blocks, then enter step (3.5);
(3.5) judge whether the cache blocks of requested data block and acquisition belongs to the same area; If so, step (3.6) is then entered; If not, then step (3.7) is entered;
(3.6) judge whether requested data block and caching data block belong to same subregion, if so, then enter step (3.4), from buffer queue, obtain next cache blocks; If not, then step (3.7) is entered;
(3.7) from Hash table, region temperature PrA corresponding to the cache blocks region temperature PrB corresponding with requested data block is searched respectively by data block number; If PrB is greater than c*PrA, then enter step (3.10); Otherwise, enter step (3.8); Wherein c is comparative factor;
(3.8) repeat step (3.4) ~ (3.7), until requested data block region temperature is completeer with the region temperature of data blocks all in buffer queue, enter step (3.9);
(3.9) read-write requests is directed to address corresponding to disk, requested data block is write disk;
(3.10) read-write requests is directed to address corresponding to current cache, requested data block is write the space at the cache blocks place of current selection.
5. buffer memory management method as claimed in claim 4, it is characterized in that, comparative factor c gets the value being greater than 1.
6. the buffer memory management method as described in claim 4 or 5, is characterized in that, each disk areas Further Division is become the subregion that two equal, and manages described subregion by binary tree.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510187454.9A CN104794064B (en) | 2015-04-21 | 2015-04-21 | A kind of buffer memory management method based on region temperature |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510187454.9A CN104794064B (en) | 2015-04-21 | 2015-04-21 | A kind of buffer memory management method based on region temperature |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104794064A true CN104794064A (en) | 2015-07-22 |
| CN104794064B CN104794064B (en) | 2017-09-29 |
Family
ID=53558872
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510187454.9A Active CN104794064B (en) | 2015-04-21 | 2015-04-21 | A kind of buffer memory management method based on region temperature |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104794064B (en) |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106027642A (en) * | 2016-05-19 | 2016-10-12 | 乐视控股（北京）有限公司 | Method and system for determining number of disks of CDN (Content Delivery Network) node |
| CN107153707A (en) * | 2017-05-12 | 2017-09-12 | 华中科技大学 | A kind of Hash table construction method and system for nonvolatile memory |
| CN107256235A (en) * | 2017-05-19 | 2017-10-17 | 武汉璞华大数据技术有限公司 | A kind of caching system hot spot data access method |
| CN107526546A (en) * | 2017-08-25 | 2017-12-29 | 深圳大学 | A kind of Spark distributed computational datas processing method and system |
| CN108376054A (en) * | 2018-01-30 | 2018-08-07 | 北京泰尔英福网络科技有限责任公司 | A kind of processing method and processing device that mark data is indexed |
| CN108762664A (en) * | 2018-02-05 | 2018-11-06 | 杭州电子科技大学 | A kind of solid state disk page grade buffer queue management method |
| CN108763110A (en) * | 2018-03-22 | 2018-11-06 | 新华三技术有限公司 | A kind of data cache method and device |
| CN109446114A (en) * | 2018-10-12 | 2019-03-08 | 咪咕文化科技有限公司 | A kind of spatial data caching method, device and storage medium |
| CN110249318A (en) * | 2017-02-07 | 2019-09-17 | 华为技术有限公司 | Cache replacement system and method |
| CN110990300A (en) * | 2019-12-20 | 2020-04-10 | 山东方寸微电子科技有限公司 | Cache memory replacement method and system based on use heat |
| CN111414132A (en) * | 2019-01-07 | 2020-07-14 | 爱思开海力士有限公司 | Main storage device with heterogeneous memory, computer system and data management method |
| CN111858403A (en) * | 2020-07-17 | 2020-10-30 | 苏州浪潮智能科技有限公司 | Cache data heat management method and system based on probability to access frequency counting |
| CN111858405A (en) * | 2020-07-10 | 2020-10-30 | 苏州浪潮智能科技有限公司 | Data caching method and device for distributed storage |
| CN112181870A (en) * | 2020-09-17 | 2021-01-05 | 重庆大学 | Memory page management method, device and equipment and readable storage medium |
| CN112306823A (en) * | 2019-07-31 | 2021-02-02 | 上海哔哩哔哩科技有限公司 | Disk management method, system, device and computer readable storage medium |
| CN112491939A (en) * | 2019-09-12 | 2021-03-12 | 上海哔哩哔哩科技有限公司 | Multimedia resource scheduling method and system |
| CN113094004A (en) * | 2021-05-13 | 2021-07-09 | 深圳市得一微电子有限责任公司 | Mirror image mapping optimization processing method for specific regular data in storage equipment |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5778430A (en) * | 1996-04-19 | 1998-07-07 | Eccs, Inc. | Method and apparatus for computer disk cache management |
| WO2006138249A2 (en) * | 2005-06-14 | 2006-12-28 | Ccor Solutions | Caching of information according to popularity |
| CN103150136A (en) * | 2013-03-25 | 2013-06-12 | 中国人民解放军国防科学技术大学 | Implementation method of least recently used (LRU) policy in solid state drive (SSD)-based high-capacity cache |
| CN103488638A (en) * | 2012-06-11 | 2014-01-01 | 北京大学 | Optimization method for result cache replacement |
-
2015
- 2015-04-21 CN CN201510187454.9A patent/CN104794064B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5778430A (en) * | 1996-04-19 | 1998-07-07 | Eccs, Inc. | Method and apparatus for computer disk cache management |
| WO2006138249A2 (en) * | 2005-06-14 | 2006-12-28 | Ccor Solutions | Caching of information according to popularity |
| CN103488638A (en) * | 2012-06-11 | 2014-01-01 | 北京大学 | Optimization method for result cache replacement |
| CN103150136A (en) * | 2013-03-25 | 2013-06-12 | 中国人民解放军国防科学技术大学 | Implementation method of least recently used (LRU) policy in solid state drive (SSD)-based high-capacity cache |
Non-Patent Citations (1)
| Title |
|---|
| SAI HUANG等: "Improving Flash-based Disk Cache with Lazy Adaptive Replacement", 《2013 IEEE 29TH SYMPOSIUM ON MASS STORAGE SYSTEMS AND TECHNOLOGIES》 * |
Cited By (31)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106027642A (en) * | 2016-05-19 | 2016-10-12 | 乐视控股（北京）有限公司 | Method and system for determining number of disks of CDN (Content Delivery Network) node |
| CN110249318A (en) * | 2017-02-07 | 2019-09-17 | 华为技术有限公司 | Cache replacement system and method |
| CN107153707A (en) * | 2017-05-12 | 2017-09-12 | 华中科技大学 | A kind of Hash table construction method and system for nonvolatile memory |
| CN107153707B (en) * | 2017-05-12 | 2020-08-14 | 华中科技大学 | Hash table construction method and system for nonvolatile memory |
| CN107256235A (en) * | 2017-05-19 | 2017-10-17 | 武汉璞华大数据技术有限公司 | A kind of caching system hot spot data access method |
| CN107526546A (en) * | 2017-08-25 | 2017-12-29 | 深圳大学 | A kind of Spark distributed computational datas processing method and system |
| CN107526546B (en) * | 2017-08-25 | 2020-09-11 | 深圳大学 | Spark distributed computing data processing method and system |
| CN108376054B (en) * | 2018-01-30 | 2020-11-03 | 中国信息通信研究院 | Processing method and device for indexing identification data |
| CN108376054A (en) * | 2018-01-30 | 2018-08-07 | 北京泰尔英福网络科技有限责任公司 | A kind of processing method and processing device that mark data is indexed |
| CN108762664B (en) * | 2018-02-05 | 2021-03-16 | 杭州电子科技大学 | Solid state disk page-level cache region management method |
| CN108762664A (en) * | 2018-02-05 | 2018-11-06 | 杭州电子科技大学 | A kind of solid state disk page grade buffer queue management method |
| CN108763110B (en) * | 2018-03-22 | 2021-01-26 | 新华三技术有限公司 | Data caching method and device |
| CN108763110A (en) * | 2018-03-22 | 2018-11-06 | 新华三技术有限公司 | A kind of data cache method and device |
| CN109446114A (en) * | 2018-10-12 | 2019-03-08 | 咪咕文化科技有限公司 | A kind of spatial data caching method, device and storage medium |
| CN109446114B (en) * | 2018-10-12 | 2020-12-18 | 咪咕文化科技有限公司 | Spatial data caching method and device and storage medium |
| CN111414132B (en) * | 2019-01-07 | 2024-03-12 | 爱思开海力士有限公司 | Main storage device with heterogeneous memory, computer system and data management method |
| CN111414132A (en) * | 2019-01-07 | 2020-07-14 | 爱思开海力士有限公司 | Main storage device with heterogeneous memory, computer system and data management method |
| CN112306823A (en) * | 2019-07-31 | 2021-02-02 | 上海哔哩哔哩科技有限公司 | Disk management method, system, device and computer readable storage medium |
| CN112306823B (en) * | 2019-07-31 | 2022-05-10 | 上海哔哩哔哩科技有限公司 | Disk management method, system, device and computer readable storage medium |
| CN112491939B (en) * | 2019-09-12 | 2022-12-27 | 上海哔哩哔哩科技有限公司 | Multimedia resource scheduling method and system |
| CN112491939A (en) * | 2019-09-12 | 2021-03-12 | 上海哔哩哔哩科技有限公司 | Multimedia resource scheduling method and system |
| CN110990300B (en) * | 2019-12-20 | 2021-12-14 | 山东方寸微电子科技有限公司 | Cache memory replacement method and system based on use heat |
| CN110990300A (en) * | 2019-12-20 | 2020-04-10 | 山东方寸微电子科技有限公司 | Cache memory replacement method and system based on use heat |
| CN111858405B (en) * | 2020-07-10 | 2022-07-19 | 苏州浪潮智能科技有限公司 | Data caching method and device for distributed storage |
| CN111858405A (en) * | 2020-07-10 | 2020-10-30 | 苏州浪潮智能科技有限公司 | Data caching method and device for distributed storage |
| CN111858403B (en) * | 2020-07-17 | 2022-07-08 | 苏州浪潮智能科技有限公司 | Cache data heat management method and system based on probability to access frequency counting |
| CN111858403A (en) * | 2020-07-17 | 2020-10-30 | 苏州浪潮智能科技有限公司 | Cache data heat management method and system based on probability to access frequency counting |
| CN112181870B (en) * | 2020-09-17 | 2022-10-28 | 重庆大学 | Memory page management method, device and equipment and readable storage medium |
| CN112181870A (en) * | 2020-09-17 | 2021-01-05 | 重庆大学 | Memory page management method, device and equipment and readable storage medium |
| CN113094004A (en) * | 2021-05-13 | 2021-07-09 | 深圳市得一微电子有限责任公司 | Mirror image mapping optimization processing method for specific regular data in storage equipment |
| CN113094004B (en) * | 2021-05-13 | 2023-11-03 | 得一微电子股份有限公司 | Data mirror image mapping optimization processing method aiming at specific rule in storage equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104794064B (en) | 2017-09-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104794064A (en) | Cache management method based on region heat degree | |
| CN102760101B (en) | SSD-based (Solid State Disk) cache management method and system | |
| KR101726824B1 (en) | Efficient Use of Hybrid Media in Cache Architectures | |
| CN107193646B (en) | High-efficiency dynamic page scheduling method based on mixed main memory architecture | |
| EP3210121B1 (en) | Cache optimization technique for large working data sets | |
| Jiang et al. | S-FTL: An efficient address translation for flash memory by exploiting spatial locality | |
| US10552317B2 (en) | Cache allocation in a computerized system | |
| CN107622022B (en) | Cache over-provisioning in a data storage device | |
| CN104572491B (en) | A kind of read buffer management method and device based on solid state hard disc | |
| CN103257935B (en) | A kind of buffer memory management method and application thereof | |
| CN108762664B (en) | Solid state disk page-level cache region management method | |
| CN104834607B (en) | A kind of hit rate for improving distributed caching and the method for reducing solid state hard disc abrasion | |
| US20100325352A1 (en) | Hierarchically structured mass storage device and method | |
| US7818505B2 (en) | Method and apparatus for managing a cache memory in a mass-storage system | |
| KR20180108513A (en) | Hardware based map acceleration using a reverse cache table | |
| CN103136121A (en) | Cache management method for solid-state disc | |
| KR20180007688A (en) | Limiting access operations in a data storage device | |
| CN108845957B (en) | Replacement and write-back self-adaptive buffer area management method | |
| CN103984648A (en) | Method to throttle rate of data caching for improved I/O performance | |
| JP6711121B2 (en) | Information processing apparatus, cache memory control method, and cache memory control program | |
| CN106569732B (en) | Data migration method and device | |
| WO2012166050A1 (en) | Buffer management apparatus and method | |
| CN106527988A (en) | SSD (Solid State Drive) data migration method and device | |
| US20140325161A1 (en) | Collaborative caching | |
| Liu et al. | Raf: A random access first cache management to improve SSD-based disk cache |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| EXSB | Decision made by sipo to initiate substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |